기존의 비전 기반 매니퓰레이터 시스템은 고정된 카메라의 위치로 인해 시야가 좁거나 물체를 가릴 수 있는 한계점이 있습니다. 저희 연구실은 로봇 핸드에 센서와 제어기가 포함된 인터페이스를 구축함으로써 물체의 인식뿐만 아니라 인지와 제어까지도 할 수 있는 비전 기반 지능형 로봇 핸드를 연구하고 있습니다.

 

Robotic Palm

Soft Robotic Palm with Tunable Stiffness Using Dual-Layered Particle Jamming Mechanism

This project presents a novel robotic palm with a dual-layered structure designed to yield high surface conformity and controllable rigidity for enhanced grasping performance. It comprises a vacuum chamber for adjusting the stiffness of the palm via particle jamming and an air chamber for actively controlling the palm deformation. An auto-jamming control scheme that automatically solidifies the palm by sensing the internal pressure of the palm without any tactile sensors or visual feedback was also proposed.

 
Dual-layered robotic palm.png
 

Demonstration of multimodal grasping

The robotic palm allows multimodal grasping with a variety
of different grasping strategies. The palm provides a stable
base for a power grasp, providing high surface conformity to
any arbitrary shape of an object in contact and also high slip
resistance.

 
Enhanced power grasp.png
 

Alternative grasping strategy

 

Pick-and-place scenario